Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method for processing information by a processing device, the method comprising: receiving a user query; inferring a user query intention from the user query to develop an inferred user intention; detecting a query type of the inferred user intention selected from a set of query types comprising a person type, an organization type, and an event type; identifying a plurality of information categories based on the query type; searching for information within each of the plurality of information categories based on identifying the plurality of information categories, wherein the searching is further based on natural language processing of a corpus of documents having multiple modalities comprising at least one of text, audio and video; identifying a plurality of items in the searched information for each of the plurality of information categories, wherein each of the plurality of items comprises a span of text from the corpus of documents including two or more entities and a relation mention explicitly describing a relation between the two or more entities; organizing the items into a plurality of equivalence classes, wherein each item having a same equivalence class comprises an equivalent relation mention; selecting a representative item from the plurality of items for each of the equivalence classes; and automatically generating a page in response to the user query by adaptively building a template with a plurality of page elements that correspond to the plurality of information categories based on the inferred user intention, wherein each of the plurality of page elements displays the searched information for a single information category from the plurality of information categories based on the selected representative items.
This invention relates to a method for processing user queries to generate structured, intent-based responses. The method addresses the challenge of retrieving and organizing relevant information from diverse data sources in response to user queries, particularly when the queries involve complex or ambiguous intentions. The system receives a user query and infers the underlying intention, classifying it into one of several predefined types, such as person, organization, or event. Based on the query type, the system identifies relevant information categories and searches a corpus of documents—comprising text, audio, and video—using natural language processing (NLP) techniques. The search results are analyzed to extract items containing spans of text that describe relationships between entities, such as connections between people, organizations, or events. These items are grouped into equivalence classes based on shared relationship descriptions, and a representative item is selected from each class. Finally, the system generates a dynamically structured page that organizes the retrieved information into distinct sections corresponding to the identified information categories, presenting the most relevant and representative items for each. This approach enhances information retrieval by adapting the output format to the user's inferred intent, improving clarity and relevance in responses.
2. The method of claim 1 , further comprising: when the user query selects a person who has a political status, detecting the political status, and identifying the information categories comprising at least one of an election campaign, public appearances, statements, and public service history based on detecting the political status.
This invention relates to a method for processing user queries involving individuals with political status. The method enhances information retrieval by automatically detecting when a queried person holds a political role and then categorizing relevant information into specific domains. When a user searches for a politically affiliated individual, the system identifies their political status and filters or organizes information into predefined categories such as election campaigns, public appearances, statements, and public service history. This ensures that users receive contextually relevant results tailored to the political context of the queried person. The method improves search efficiency by prioritizing politically significant data over general biographical details, addressing the challenge of retrieving precise, role-specific information in political research or public discourse. The system dynamically adjusts information categorization based on the detected political status, ensuring accuracy and relevance. This approach is particularly useful for journalists, researchers, or citizens seeking detailed insights into political figures' activities and backgrounds.
3. The method of claim 1 , further comprising: when the user query selects a company identifying the information categories comprising at least one of recent news about the company, information on the company's top officials, and press releases for the company based on the user query selecting the company.
This invention relates to a system for retrieving and displaying company-related information in response to user queries. The problem addressed is the difficulty in efficiently accessing relevant and up-to-date information about a company, such as recent news, key personnel details, and press releases, from a single source. The solution involves a method that processes a user query to identify a specific company and then retrieves and presents information categorized into at least one of three types: recent news about the company, information on the company's top officials, and press releases for the company. The system dynamically filters and organizes the information based on the user's selection, ensuring that the most pertinent details are displayed. This approach streamlines the information retrieval process, reducing the need for users to search multiple sources or manually filter results. The method enhances user experience by providing a structured and targeted presentation of company-specific data, improving efficiency and accuracy in accessing critical business intelligence.
4. The method of claim 1 , further comprising: when the user query selects an event identifying the information categories comprising at least one of news items about the event and reactions to the event based on the user query selecting the event.
This invention relates to a method for processing user queries to retrieve information about events, including news items and reactions to those events. The method involves analyzing a user query to identify an event of interest and then categorizing the information associated with that event into at least two distinct types: news items about the event and reactions to the event. The system dynamically filters and presents the information based on the user's selection of the event, ensuring that the retrieved data is relevant to the specific event and the type of information requested. This approach enhances the precision of information retrieval by distinguishing between factual news coverage and user or community reactions, allowing users to access tailored content efficiently. The method may also involve additional steps such as ranking or prioritizing the retrieved information based on relevance, recency, or other criteria to improve user experience. The system ensures that the information is presented in a structured manner, making it easier for users to navigate and understand the context of the event. This method is particularly useful in applications where timely and accurate event-based information is critical, such as news aggregation, social media monitoring, or event tracking platforms.
5. The method of claim 4 , wherein entities in the event are identified and relevant information about the entities is searched.
This invention relates to event processing systems that identify and analyze entities within events to extract relevant information. The technology addresses the challenge of efficiently recognizing and retrieving contextual details about entities involved in events, such as people, objects, or locations, to enhance decision-making, security, or operational efficiency. The method involves detecting entities within an event, which may include individuals, objects, or other relevant subjects. Once identified, the system searches for and retrieves pertinent information about these entities from various data sources. This information may include historical data, relationships, or contextual details that provide deeper insights into the event. The process ensures that the extracted data is relevant to the specific entities and the event context, improving accuracy and usefulness. The system may also categorize entities based on predefined criteria, such as roles or significance, to prioritize information retrieval. By integrating entity identification with information search, the method enhances situational awareness, enabling better responses to dynamic events. Applications include surveillance, fraud detection, customer service, and automated decision-making systems. The invention improves upon existing systems by automating entity recognition and contextual information retrieval, reducing manual effort and increasing efficiency.
6. A non-transitory computer program storage device embodying instructions executable by a processor, the non-transitory computer program storage device comprising storage memory configured to store: program code that receives a user query; program code that infers a user query intention from the user query to develop an inferred user intention; program code that detects a query type of the inferred user intention selected from a set of query types comprising a person type, an organization type, and an event type; program code that identifies a plurality of information categories based on the query type; program code that searches for information within each of the plurality of information categories based on identifying the plurality of information categories, wherein the searching is further based on natural language processing of a corpus of documents having multiple modalities comprising at least one of text, audio and video; program code that identifies a plurality of items in the searched information for each of the plurality of information categories, wherein each of the plurality of items comprises a span of text from the corpus of documents including two or more entities and a relation mention explicitly describing a relation between the two or more entities; program code that organizes the items into a plurality of equivalence classes, wherein each item having a same equivalence class comprises an equivalent relation mention; program code that selects a representative item from the plurality of items for each of the equivalence classes; and program code that automatically generates a page in response to the user query by adaptively building a template with a plurality of page elements that correspond to the plurality of information categories based on the inferred user intention, wherein each of the plurality of page elements displays the searched information for a single information category from the plurality of information categories based on the selected representative items.
This invention relates to a system for processing user queries to generate structured, intent-aware responses by analyzing and organizing information from multimodal documents. The system addresses the challenge of retrieving and presenting relevant information in a coherent, categorized format based on the inferred intent behind a user's query. The system receives a user query and infers its intent, classifying it into one of several predefined types, such as person, organization, or event. Based on the query type, the system identifies relevant information categories and searches a corpus of documents—comprising text, audio, and video—using natural language processing. The search results are filtered to extract items containing spans of text that describe relationships between entities. These items are grouped into equivalence classes based on shared relational mentions, and a representative item is selected from each class. Finally, the system generates a dynamically structured page that organizes the retrieved information into distinct sections corresponding to the identified categories, displaying the representative items for each. This approach ensures that responses are tailored to the user's intent while maintaining clarity and relevance.
7. The non-transitory computer program storage device of claim 6 , further comprising: program code that, when the user query selects a person who has a political status, detects the political status, identifies the information categories comprising at least one of an election campaign, public appearances, statements, and public service history based on detecting the political status.
This invention relates to a computer program for processing user queries about individuals with political status. The system detects when a user query targets a person with political status and automatically identifies relevant information categories associated with that status. These categories include election campaigns, public appearances, statements, and public service history. The program dynamically filters or organizes information based on the detected political status to provide more relevant results. The underlying system involves a non-transitory computer storage device containing executable code that performs these operations. The program may also include additional features such as analyzing the user query to determine the context or intent behind the request, and then tailoring the information retrieval process accordingly. The invention aims to improve the efficiency and relevance of information retrieval for politically significant individuals by leveraging their status to prioritize or categorize specific types of data. This approach helps users quickly access pertinent information without needing to manually specify the desired categories. The system may integrate with existing search engines or databases to enhance their functionality for political figures.
8. The non-transitory computer program storage device of claim 6 , further comprising program code that, when the user query selects a company, identifies the information categories comprising at least one of recent news about the company, information on the company's top officials, and press releases for the company based on the user query selecting the company.
This invention relates to a computer program for retrieving and displaying company-related information in response to user queries. The system addresses the challenge of efficiently organizing and presenting diverse company data, such as news, executive details, and press releases, in a structured manner to enhance user accessibility. The program operates by first receiving a user query that selects a specific company. Upon selection, the system identifies and retrieves relevant information categories associated with the company. These categories include recent news articles, profiles of the company's top officials, and official press releases. The retrieved information is then displayed to the user in a consolidated format, allowing for quick access to key details about the company. The system ensures that the information is dynamically updated, reflecting the latest developments and ensuring users have access to current data. By categorizing and presenting the information in a structured way, the program simplifies the process of gathering comprehensive company insights, making it particularly useful for researchers, investors, and business analysts who require timely and organized data. The invention improves efficiency by reducing the need for manual searches across multiple sources.
9. The non-transitory computer program storage device of claim 6 , further comprising program code that, when the user query selects an event, identifies the information categories comprising at least one of news items about the event and reactions to the event based on the user query selecting the event.
This invention relates to a computer program for organizing and retrieving event-related information. The system addresses the challenge of efficiently accessing diverse information about a specific event, including news items and user reactions, in a structured manner. The program operates by storing event data and associated information categories, which may include news articles, social media posts, or other reactions to the event. When a user selects an event, the program identifies and retrieves relevant information categories, such as news items directly related to the event and user-generated reactions to it. The system dynamically filters and presents this information based on the user's selection, ensuring that the retrieved data is contextually relevant to the chosen event. This approach enhances information retrieval by categorizing and linking event-related content, allowing users to quickly access both factual news and public reactions in a unified interface. The program may also include additional features, such as user authentication, data storage management, and interfaces for inputting or modifying event-related information. The overall goal is to streamline the process of gathering and analyzing event-specific data from multiple sources.
10. The non-transitory computer program storage device of claim 9 , wherein entities in the event are identified and relevant information about the entities is searched.
This invention relates to a computer program for processing event data to identify and analyze entities involved in the event. The system captures event data from various sources, such as logs, sensors, or user inputs, and processes the data to detect entities like people, devices, or locations associated with the event. Once identified, the system retrieves relevant information about these entities from external or internal databases. This information may include historical data, relationships, or contextual details that provide deeper insights into the event. The system then correlates the retrieved information with the event data to enhance understanding, decision-making, or automated responses. The invention improves event analysis by automating entity identification and information retrieval, reducing manual effort and increasing accuracy. Applications include cybersecurity, logistics, and event monitoring, where understanding entity roles and relationships is critical. The system may integrate with existing data processing frameworks or operate as a standalone tool, ensuring flexibility in deployment.
11. A method for processing information by a processing device, the method comprising: receiving a user query; inferring a user query intention from the user query to develop an inferred user intention; detecting a query type based on the inferred user intention; searching for a plurality of information categories in a corpus of documents based on the query type; identifying a plurality of items for each of the plurality of information categories based on the search, wherein each of the plurality of items comprises a span of text from the corpus of documents including two or more entities and a relation mention explicitly describing a relation between the two or more entities; organizing the items into a plurality of equivalence classes, wherein each item having a same equivalence class comprises an equivalent relation mention; selecting a representative item from the plurality of items for each of the plurality of equivalence classes; and generating a page based on the query type, the page comprising a plurality of tabs, wherein each tab contains the representative items corresponding to the plurality of equivalence classes of an information category from the plurality of information categories.
This invention relates to information retrieval and processing, specifically improving the way search systems interpret user queries and present relevant data. The problem addressed is the difficulty in accurately understanding user intent and organizing search results in a structured, meaningful way, particularly when queries involve complex relationships between entities. The method involves a processing device receiving a user query and analyzing it to infer the user's intent. Based on this inferred intent, the system detects the type of query (e.g., factual, comparative, or relational). The system then searches a corpus of documents for multiple information categories relevant to the query type. For each category, it identifies text spans containing two or more entities and a relation explicitly describing their connection. These text spans are grouped into equivalence classes, where each class contains items with the same relational description. A representative item is selected from each equivalence class, and a page is generated with multiple tabs. Each tab displays representative items from different equivalence classes within a specific information category, allowing users to explore structured, relation-based results. This approach enhances search precision and usability by organizing information around inferred relationships.
12. The method of claim 11 , further comprising: scoring each of the equivalence classes; and prioritizing the equivalence classes based on the scoring.
This invention relates to a method for analyzing and prioritizing equivalence classes in a technical or data processing system. The method addresses the problem of efficiently identifying and managing equivalence classes, which are groups of elements or data points that are considered equivalent under certain conditions. The invention improves upon prior approaches by introducing a scoring mechanism to evaluate the relevance or importance of each equivalence class, followed by prioritization based on these scores. This allows for more effective decision-making, resource allocation, or further processing steps in systems where equivalence classes are used, such as in data clustering, pattern recognition, or software testing. The scoring and prioritization steps enhance the usability of equivalence classes by ensuring that the most significant or impactful groups are processed first, optimizing computational efficiency and accuracy. The method can be applied in various domains, including machine learning, software development, and data analysis, where equivalence classes play a critical role in reducing complexity and improving system performance.
Unknown
June 30, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.